When you perform embedding retrieval, use this component first to transform your query into a vector. Then, the embedding Retriever will use the vector to search for similar or relevant documents.


Most common position in a pipeline	Before an embedding Retriever in a query/RAG pipeline
Mandatory init variables	"token": A HF API token. Can be set with `HF_API_TOKEN` or `HF_TOKEN` env var.
Mandatory run variables	"text": A string
Output variables	"embedding": A list of float numbers
API reference	Embedders
GitHub link	https://github.com/deepset-ai/haystack/blob/main/haystack/components/embedders/sentence_transformers_text_embedder.py

Overview

This component should be used to embed a simple string (such as a query) into a vector. For embedding lists of documents, use the SentenceTransformersDocumentEmbedder, which enriches the document with the computed embedding, known as vector.

The component uses a HF_API_TOKEN environment variable by default. Otherwise, you can pass a Hugging Face API token at initialization with token:

text_embedder = SentenceTransformersTextEmbedder(token=Secret.from_token("<your-api-key>"))

Compatible Models

The default embedding model is `sentence-transformers/all-mpnet-base-v2`. You can specify another model with the model parameter when initializing this component.

See the original models in the Sentence Transformers documentation.

Nowadays, most of the models in the Massive Text Embedding Benchmark (MTEB) Leaderboard are compatible with Sentence Transformers.
You can look for compatibility in the model card: an example related to BGE models.

Instructions

Some recent models that you can find in MTEB require prepending the text with an instruction to work better for retrieval.
For example, if you use BAAI/bge-large-en-v1.5, you should prefix your query with the following instruction: “Represent this sentence for searching relevant passages:”

This is how it works with SentenceTransformersTextEmbedder:

instruction = "Represent this sentence for searching relevant passages:"
embedder = SentenceTransformersTextEmbedder(
	*model="*BAAI/bge-large-en-v1.5",
	prefix=instruction)

👍
If you create a Text Embedder and a Document Embedder based on the same model, Haystack takes care of using the same resource behind the scenes in order to save resources.

Usage

On its own

from haystack.components.embedders import SentenceTransformersTextEmbedder

text_to_embed = "I love pizza!"

text_embedder = SentenceTransformersTextEmbedder()
text_embedder.warm_up()

print(text_embedder.run(text_to_embed))

# {'embedding': [-0.07804739475250244, 0.1498992145061493,, ...]}

In a pipeline

from haystack import Document
from haystack import Pipeline
from haystack.document_stores.in_memory import InMemoryDocumentStore
from haystack.components.embedders import SentenceTransformersTextEmbedder, SentenceTransformersDocumentEmbedder
from haystack.components.retrievers.in_memory import InMemoryEmbeddingRetriever

document_store = InMemoryDocumentStore(embedding_similarity_function="cosine")

documents = [Document(content="My name is Wolfgang and I live in Berlin"),
             Document(content="I saw a black horse running"),
             Document(content="Germany has many big cities")]

document_embedder = SentenceTransformersDocumentEmbedder()
document_embedder.warm_up()
documents_with_embeddings = document_embedder.run(documents)['documents']
document_store.write_documents(documents_with_embeddings)

query_pipeline = Pipeline()
query_pipeline.add_component("text_embedder", SentenceTransformersTextEmbedder())
query_pipeline.add_component("retriever", InMemoryEmbeddingRetriever(document_store=document_store))
query_pipeline.connect("text_embedder.embedding", "retriever.query_embedding")

query = "Who lives in Berlin?"

result = query_pipeline.run({"text_embedder":{"text": query}})

print(result['retriever']['documents'][0])

# Document(id=..., mimetype: 'text/plain', 
#  text: 'My name is Wolfgang and I live in Berlin')